INDEX

Explanations

references to professional experience and expertise

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

atase

-0.46

 tetto

-0.45

 fhort

-0.45

letoe

-0.44

 corações

-0.43

 zichzelf

-0.43

 dicendo

-0.43

 borboleta

-0.43

 meninos

-0.42

 verwij

-0.42

POSITIVE LOGITS

 experience

1.82

experience

1.70

 Experience

1.66

Experience

1.65

 EXPERIENCE

1.52

 experiences

1.50

EXPERIENCE

1.48

 experien

1.45

 experienced

1.45

 experiencia

1.41

Activations Density 0.106%

references to professional experience and expertise

No Comments

No Known Activations